We investigate the usage of an adaptive method, the Iterative Adaptive Approach (IAA), in combination with
a maximum a posteriori (MAP) estimate to reconstruct high resolution SAR images that are both sparse and
accurate. IAA is a nonparametric weighted least squares algorithm that is robust and user parameter-free. IAA
has been shown to reconstruct SAR images with excellent side lobes suppression and high resolution enhancement.
We first reconstruct the SAR images using IAA, and then we enforce sparsity by using MAP with a sparsity
inducing prior. By coupling these two methods, we can produce a sparse and accurate high resolution image
that are conducive for feature extractions and target classification applications. In addition, we show how IAA
can be made computationally efficient without sacrificing accuracies, a desirable property for SAR applications
where the size of the problems is quite large. We demonstrate the success of our approach using the Air Force
Research Lab's "Gotcha Volumetric SAR Data Set Version 1.0" challenge dataset. Via the widely used FFT,
individual vehicles contained in the scene are barely recognizable due to the poor resolution and high side lobe
nature of FFT. However with our approach clear edges, boundaries, and textures of the vehicles are obtained.